Files
CosmicClash/server/api/outbox_test.go
T
Josh Creek 1dd05c75f1 fix(server): repair the initial-connect outbox envelope and unblock dispatch
ApplyInitialConnectPlan wrote a payload of {match_id,state,action},
omitting event, revision, resource_id, occurred_at and player_ids --
every field deliverStateOutboxEvent requires. Delivery rejected the row,
dispatch returned on the first error so it was never acknowledged, and
because reads are ordered oldest-first it was retried ahead of every
later state_changed event on every 100ms poll. One initial-connect
transition therefore blocked lifecycle delivery for all matches, not
just its own.

Two independent fixes, since either alone leaves the system fragile:

Build envelopes through one validating helper (MarshalOutboxEnvelope)
and convert all five writers to it. A writer that omits a required
field now fails its own transaction instead of committing a row that
can only ever poison the queue. The helper takes revision as int64 so
the -1 "nothing matched" sentinel some CTEs return surfaces as an error
rather than wrapping to a huge uint64.

Make dispatch resilient regardless: a delivery failure is now counted
against that row and the batch continues, with the row dead-lettered
after MaxOutboxDeliveryAttempts so a poison event degrades to one lost
notification instead of a stalled queue. Ordering within an aggregate
is still honoured -- later events of a failed match are deferred, so no
client observes that match's newer state before its older state. An ack
failure still stops the batch, being a database rather than a payload
problem.

Initial-connect events now address every participant, not just the
connected ones: a no-show needs to learn their ticket was failed and a
penalty applied.
2026-09-05 10:17:16 +01:00

158 lines
6.6 KiB
Go

package api
import (
"context"
"encoding/json"
"errors"
"slices"
"testing"
"time"
"github.com/cosmic-clash/cosmic-clash/server/store"
)
func TestDeliverProposalOutboxEventPublishesEveryTarget(t *testing.T) {
service := &Service{}
first := service.getEventHub().subscribe("player-a")
second := service.getEventHub().subscribe("player-b")
defer service.getEventHub().unsubscribe(first)
defer service.getEventHub().unsubscribe(second)
payload, err := json.Marshal(map[string]any{
"event": "proposal_changed", "revision": uint64(0), "resource_id": "proposal_1234567890",
"occurred_at": time.Unix(1000, 0).UTC(), "state": "OPEN", "player_ids": []string{"player-a", "player-b"},
})
if err != nil {
t.Fatal(err)
}
if err := deliverProposalOutboxEvent(context.Background(), store.OutboxEvent{EventID: "event-1", Payload: payload}, service); err != nil {
t.Fatalf("deliver proposal event: %v", err)
}
for name, subscriber := range map[string]*eventSubscriber{"player-a": first, "player-b": second} {
select {
case <-subscriber.queue:
case <-time.After(time.Second):
t.Fatalf("%s did not receive targeted proposal event", name)
}
}
}
func TestDeliverProposalOutboxEventRejectsMalformedOrUntargetedRows(t *testing.T) {
service := &Service{}
for name, event := range map[string]store.OutboxEvent{
"malformed": {Payload: []byte("{")},
"wrong event": {Payload: []byte(`{"event":"match_completed","resource_id":"match-1","player_ids":["player-a"]}`)},
"missing target": {Payload: []byte(`{"event":"proposal_changed","resource_id":"proposal-1","player_ids":[]}`)},
} {
t.Run(name, func(t *testing.T) {
if err := deliverProposalOutboxEvent(context.Background(), event, service); err == nil {
t.Fatal("malformed or untargeted event accepted")
}
})
}
}
func TestDeliverResultOutboxEventRejectsMalformedRows(t *testing.T) {
for _, event := range []store.OutboxEvent{
{EventType: "proposal_changed", AggregateID: "match-1", Revision: 1, Payload: []byte(`{}`)},
{EventType: "match_completed", AggregateID: "", Revision: 1, Payload: []byte(`{}`)},
{EventType: "match_completed", AggregateID: "match-1", Revision: 1, Payload: []byte(`not-json`)},
} {
if err := deliverResultOutboxEvent(nil, nil, event, &Service{}); err == nil {
t.Fatalf("invalid result event accepted: %+v", event)
}
}
}
func TestDeliverStateOutboxEventValidatesRevisionAndTargets(t *testing.T) {
service := &Service{}
first := service.getEventHub().subscribe("player-a")
defer service.getEventHub().unsubscribe(first)
payload := []byte(`{"event":"state_changed","revision":4,"resource_id":"match_1234567890","occurred_at":"1970-01-01T00:16:40Z","state":"ASSIGNMENT_READY","match_id":"match-1","player_ids":["player-a"]}`)
if err := deliverStateOutboxEvent(context.Background(), store.OutboxEvent{EventType: "state_changed", AggregateID: "match_1234567890", Revision: 4, Payload: payload}, service); err != nil {
t.Fatalf("valid state event rejected: %v", err)
}
select {
case <-first.queue:
case <-time.After(time.Second):
t.Fatal("participant did not receive state event")
}
bad := []byte(`{"event":"state_changed","revision":3,"resource_id":"match_1234567890","state":"LIVE","player_ids":["player-a"]}`)
if err := deliverStateOutboxEvent(context.Background(), store.OutboxEvent{EventType: "state_changed", AggregateID: "match_1234567890", Revision: 4, Payload: bad}, service); err == nil {
t.Fatal("revision-mismatched state event accepted")
}
}
func TestDeliverStateOutboxEventRoutesLiveAbandonmentLifecycle(t *testing.T) {
service := &Service{}
first := service.getEventHub().subscribe("player-a")
second := service.getEventHub().subscribe("player-b")
defer service.getEventHub().unsubscribe(first)
defer service.getEventHub().unsubscribe(second)
payload := []byte(`{"event":"state_changed","revision":9,"resource_id":"match_1234567890","occurred_at":"1970-01-01T00:16:40Z","state":"LIVE","match_id":"match_1234567890","player_ids":["player-a","player-b"],"abandoned_player_ids":["player-a"]}`)
event := store.OutboxEvent{EventType: "state_changed", AggregateID: "match_1234567890", Revision: 9, Payload: payload}
if err := deliverStateOutboxEvent(context.Background(), event, service); err != nil {
t.Fatalf("live abandonment event rejected: %v", err)
}
for playerID, subscriber := range map[string]*eventSubscriber{"player-a": first, "player-b": second} {
select {
case packet := <-subscriber.queue:
if !json.Valid(packet) {
t.Fatalf("%s received malformed lifecycle packet %q", playerID, packet)
}
case <-time.After(time.Second):
t.Fatalf("%s did not receive live-abandonment lifecycle event", playerID)
}
}
}
// One malformed row used to abort the whole batch. Because reads are
// oldest-first and the row was never acknowledged, it was re-read ahead of
// every later event of its type on every 100ms poll -- blocking lifecycle
// delivery for all matches indefinitely, not just its own.
func TestDispatchOutboxEventsIsNotBlockedByOnePoisonRow(t *testing.T) {
delivered := []string{}
acked := []string{}
dispatcher := &store.OutboxDispatcher{
Read: func(context.Context, int) ([]store.OutboxEvent, error) { return nil, nil },
Deliver: func(_ context.Context, event store.OutboxEvent) error {
delivered = append(delivered, event.EventID)
if event.AggregateID == "match-poison" {
return errors.New("invalid state outbox payload")
}
return nil
},
Ack: func(_ context.Context, eventID string, _ time.Time) error {
acked = append(acked, eventID)
return nil
},
}
events := []store.OutboxEvent{
{EventID: "poison-1", AggregateID: "match-poison"},
{EventID: "healthy-1", AggregateID: "match-healthy"},
{EventID: "poison-2", AggregateID: "match-poison"},
{EventID: "healthy-2", AggregateID: "match-other"},
}
// nil db: the failure counter is exercised against a real PostgreSQL in
// the store integration tests; here we assert only batch progress.
err := dispatchOutboxEvents(context.Background(), nil, dispatcher, events)
if err == nil {
t.Fatal("expected the delivery failure to be reported to the caller")
}
for _, eventID := range []string{"healthy-1", "healthy-2"} {
if !slices.Contains(acked, eventID) {
t.Fatalf("%s was not acknowledged; a poison row still blocks the batch (acked=%v)", eventID, acked)
}
}
if slices.Contains(acked, "poison-1") {
t.Fatal("a failed delivery must not be acknowledged")
}
// Ordering within the failing aggregate is preserved: poison-2 must wait
// so no client sees that match's newer state before its older state.
if slices.Contains(delivered, "poison-2") {
t.Fatalf("later event of a failed aggregate was delivered out of order: %v", delivered)
}
}